论文标题
3D重建的次数视图策略
Next-Best View Policy for 3D Reconstruction
论文作者
论文摘要
手动选择观点或使用常用的飞行计划者（例如使用无人机进行大规模3D重建的圆形路径）通常会导致3D模型不完整。最近的作品依靠手工设计的启发式方法，例如信息增益来选择次要的观点。在这项工作中，我们提出了一种基于学习的算法，称为scan-rl，以学习下一步的视图（NBV）策略。为了培训和评估代理商，我们创建了Houses3K，这是3D房屋型号的数据集。我们的实验表明，与基线圆形路径相比，使用SCAN-RL可以使用较少的步骤和较短的距离扫描房屋。实验结果还表明，单个NBV策略可用于扫描多个房屋，包括训练期间未见的房屋。可以在https://github.com/darylperalta/scanrl上获得scan-rl的链接，并且可以在https://github.com/darylperalta/houses3k上找到Houses3k数据集。
Manually selecting viewpoints or using commonly available flight planners like circular path for large-scale 3D reconstruction using drones often results in incomplete 3D models. Recent works have relied on hand-engineered heuristics such as information gain to select the Next-Best Views. In this work, we present a learning-based algorithm called Scan-RL to learn a Next-Best View (NBV) Policy. To train and evaluate the agent, we created Houses3K, a dataset of 3D house models. Our experiments show that using Scan-RL, the agent can scan houses with fewer number of steps and a shorter distance compared to our baseline circular path. Experimental results also demonstrate that a single NBV policy can be used to scan multiple houses including those that were not seen during training. The link to Scan-RL is available at https://github.com/darylperalta/ScanRL and Houses3K dataset can be found at https://github.com/darylperalta/Houses3K.
